Current position: Home >> Scientific Research >> Paper Publications

A New Conjugate Gradient Method with Smoothing L-1/2 Regularization Based on a Modified Secant Equation for Training Neural Networks

Release Time:2022-12-09  Hits:

Date of Publication: 2022-10-05

Journal: NEURAL PROCESSING LETTERS

Volume: 48

Issue: 2,SI

Page Number: 955-978

ISSN: 1370-4621

Prev One:Interpretability for Neural Networks from the Perspective of Probability Density

Next One:A new training algorithm for a fuzzy perceptron and its convergence